The saturated hydraulic conductivity (K s ) of the soil is one of the main soil physical properties. Indirect estimation of this parameter using pedo-transfer functions (PTFs) has received considerable attention. The Purpose of this study was to improve the estimation of K s using fractal parameters of particle and micro-aggregate size distributions in smectitic soils. In this study 260 disturbed and undisturbed soil samples were collected from Guilan province, the north of Iran. The fractal model of Bird and Perrier was used to compute the fractal parameters of particle and micro-aggregate size distributions. The PTFs were developed by artificial neural networks (ANNs) ensemble to estimate K s by using available soil data and fractal parameters. There were found significant correlations between K s and fractal parameters of particles and microaggregates. Estimation of K s was improved significantly by using fractal parameters of soil micro-aggregates as predictors. But using geometric mean and geometric standard deviation of particles diameter did not improve K s estimations significantly. Using fractal parameters of particles and micro-aggregates simultaneously, had the most effect in the estimation of K s . Generally, fractal parameters can be successfully used as input parameters to improve the estimation of K s in the PTFs in smectitic soils. As a result, ANNs ensemble successfully correlated the fractal parameters of particles and micro-aggregates to K s .

In this study, at first, the dynamic of progressive failure of Glass-Fiber-Reinforced aluminum laminates (GLARE) under low-energy impact with intra laminar damage models implementing strain-based damage evolution laws, Puck failure criteria using ABAQUS-VUMAT, were modeled. For interface delamination, bilinear cohesive model; and for aluminum layers the Johnson-Cook model was implemented; and the fatigue life of the fiber metal laminates of GLARE subjected to impact was obtained and the numerical and experimental results of the model were compared with each other. With regard to the very good match between the numerical and experimental results, the results of the finite element model were generalized and expanded, and with the use of the multilayer neural network, the numerical model was extracted and then, by applying the meta-innovative algorithm, the maximum fatigue life of GLARE was determined at the highest level with very low-velocity impact, and the best configuration of three-layer GLARE was selected. The findings indicated that the best configuration of hybrid composite GLARE based on conventional commercial laminates that can tolerate low-velocity impacts with 18J impact energy and a 349MPa fatigue load with a frequency of 10Hz was [

No abstract

Scouring around bridge pier is a major cause of bridge instability. Thus, providing appropriate methods in order to reduce and control the scour depth have received much attention. Using a slot in the bridge piers is one of modern methods of reducing bridge local scouring. In the present study, the effects of a rectangular slot on local scour mitigation around bridge pier groups have been investigated with adaptive neurofuzzy (ANFIS) method. ANFIS shows very good learning and prediction capabilities, which makes it an efficient tool to deal with encountered uncertainties in any system like scouring. The results show that the scour depth increased in the first pier by reinforcing effect and it decreased in the rear piers because of sheltering effect in compare with single pier. In addition, application of the slot in pier groups leads to an increase in the impact of reinforcing effect and reduce the influence of sheltering effect.The use of slot is more influential in front bridge piers than the rear piers in pier groups with 4D distance, however, this effectiveness doesn't have significant difference among the piers with 2D distance and same as single pier. Laboratory experiments were conducted to create experimental training and checking data for ANFIS network. This intelligent estimator is implemented using Matlab/Simulink and the performances are investigated. The simulation results presented in this paper show the effectiveness of the developed method.

No abstract